@inproceedings{petukhova-etal-2014-interoperability,
title = "Interoperability of Dialogue Corpora through {ISO} 24617-2-based Querying",
author = "Petukhova, Volha and
Malchanau, Andrei and
Bunt, Harry",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Loftsson, Hrafn and
Maegaard, Bente and
Mariani, Joseph and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Ninth International Conference on Language Resources and Evaluation ({LREC}'14)",
month = may,
year = "2014",
address = "Reykjavik, Iceland",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2014/pdf/165_Paper.pdf",
pages = "4407--4414",
abstract = "This paper explores a way of achieving interoperability: developing a query format for accessing existing annotated corpora whose expressions make use of the annotation language defined by the standard. The interpretation of expressions in the query implements a mapping from ISO 24617-2 concepts to those of the annotation scheme used in the corpus. We discuss two possible ways to query existing annotated corpora using DiAML. One way is to transform corpora into DiAML compliant format, and subsequently query these data using XQuery or XPath. The second approach is to define a DiAML query that can be directly used to retrieve requested information from the annotated data. Both approaches are valid. The first one presents a standard way of querying XML data. The second approach is a DiAML-oriented querying of dialogue act annotated data, for which we designed an interface. The proposed approach is tested on two important types of existing dialogue corpora: spoken two-person dialogue corpora collected and annotated within the HCRC Map Task paradigm, and multiparty face-to-face dialogues of the AMI corpus. We present the results and evaluate them with respect to accuracy and completeness through statistical comparisons between retrieved and manually constructed reference annotations.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="petukhova-etal-2014-interoperability">
<titleInfo>
<title>Interoperability of Dialogue Corpora through ISO 24617-2-based Querying</title>
</titleInfo>
<name type="personal">
<namePart type="given">Volha</namePart>
<namePart type="family">Petukhova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrei</namePart>
<namePart type="family">Malchanau</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Harry</namePart>
<namePart type="family">Bunt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2014-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hrafn</namePart>
<namePart type="family">Loftsson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asuncion</namePart>
<namePart type="family">Moreno</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Reykjavik, Iceland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper explores a way of achieving interoperability: developing a query format for accessing existing annotated corpora whose expressions make use of the annotation language defined by the standard. The interpretation of expressions in the query implements a mapping from ISO 24617-2 concepts to those of the annotation scheme used in the corpus. We discuss two possible ways to query existing annotated corpora using DiAML. One way is to transform corpora into DiAML compliant format, and subsequently query these data using XQuery or XPath. The second approach is to define a DiAML query that can be directly used to retrieve requested information from the annotated data. Both approaches are valid. The first one presents a standard way of querying XML data. The second approach is a DiAML-oriented querying of dialogue act annotated data, for which we designed an interface. The proposed approach is tested on two important types of existing dialogue corpora: spoken two-person dialogue corpora collected and annotated within the HCRC Map Task paradigm, and multiparty face-to-face dialogues of the AMI corpus. We present the results and evaluate them with respect to accuracy and completeness through statistical comparisons between retrieved and manually constructed reference annotations.</abstract>
<identifier type="citekey">petukhova-etal-2014-interoperability</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/165_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>4407</start>
<end>4414</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Interoperability of Dialogue Corpora through ISO 24617-2-based Querying
%A Petukhova, Volha
%A Malchanau, Andrei
%A Bunt, Harry
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Loftsson, Hrafn
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14)
%D 2014
%8 May
%I European Language Resources Association (ELRA)
%C Reykjavik, Iceland
%F petukhova-etal-2014-interoperability
%X This paper explores a way of achieving interoperability: developing a query format for accessing existing annotated corpora whose expressions make use of the annotation language defined by the standard. The interpretation of expressions in the query implements a mapping from ISO 24617-2 concepts to those of the annotation scheme used in the corpus. We discuss two possible ways to query existing annotated corpora using DiAML. One way is to transform corpora into DiAML compliant format, and subsequently query these data using XQuery or XPath. The second approach is to define a DiAML query that can be directly used to retrieve requested information from the annotated data. Both approaches are valid. The first one presents a standard way of querying XML data. The second approach is a DiAML-oriented querying of dialogue act annotated data, for which we designed an interface. The proposed approach is tested on two important types of existing dialogue corpora: spoken two-person dialogue corpora collected and annotated within the HCRC Map Task paradigm, and multiparty face-to-face dialogues of the AMI corpus. We present the results and evaluate them with respect to accuracy and completeness through statistical comparisons between retrieved and manually constructed reference annotations.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/165_Paper.pdf
%P 4407-4414
Markdown (Informal)
[Interoperability of Dialogue Corpora through ISO 24617-2-based Querying](http://www.lrec-conf.org/proceedings/lrec2014/pdf/165_Paper.pdf) (Petukhova et al., LREC 2014)
ACL